arXiv cs.LG
· Papers
The Hamilton-Jacobi Theory of Deep Learning
arXiv:2605.28983v2 Announce Type: replace Abstract: In this paper, training a neural network is identified, exactly, as a search through Hamilton--Jacobi initial-value problems: each gradient step selects the initial data of a viscous Hamilton--Jacobi equation whose Hopf--Cole propagator best fits the observations; at